fix(core): skip empty/invalid chunks before embedding; guard OpenAI embeddings

Avoid 400 errors from OpenAI when chunker yields empty strings by filtering
invalid texts in LeannBuilder.build_index. Add validation fail-fast in
OpenAI embedding path to surface upstream issues earlier. Keeps passages and
embeddings aligned during build.

Refs #54

README.md

@@ -5,7 +5,7 @@
 <p align="center">
   <img src="https://img.shields.io/badge/Python-3.9%20%7C%203.10%20%7C%203.11%20%7C%203.12%20%7C%203.13-blue.svg" alt="Python Versions">
   <img src="https://github.com/yichuan-w/LEANN/actions/workflows/build-and-publish.yml/badge.svg" alt="CI Status">
-  <img src="https://img.shields.io/badge/Platform-Ubuntu%20%26%20Arch%20%26%20WSL%20%7C%20macOS%20(ARM64%2FIntel)-lightgrey" alt="Platform">
+  <img src="https://img.shields.io/badge/Platform-Ubuntu%20%7C%20macOS%20(ARM64%2FIntel)-lightgrey" alt="Platform">
   <img src="https://img.shields.io/badge/License-MIT-green.svg" alt="MIT License">
   <img src="https://img.shields.io/badge/MCP-Native%20Integration-blue" alt="MCP Integration">
 </p>
@@ -94,9 +94,7 @@ CC=$(brew --prefix llvm)/bin/clang CXX=$(brew --prefix llvm)/bin/clang++ uv sync
 
 **Linux:**
 ```bash
-# Ubuntu/Debian (For Arch Linux: sudo pacman -S blas lapack openblas libaio boost protobuf abseil-cpp zeromq)
+sudo apt-get install libomp-dev libboost-all-dev protobuf-compiler libabsl-dev libmkl-full-dev libaio-dev libzmq3-dev
-sudo apt-get update && sudo apt-get install -y libomp-dev libboost-all-dev protobuf-compiler libabsl-dev libmkl-full-dev libaio-dev libzmq3-dev
-
 uv sync
 ```
 
@@ -484,9 +482,6 @@ leann ask my-docs --interactive
 
 # List all your indexes
 leann list
-
-# Remove an index
-leann remove my-docs
 ```
 
 **Key CLI features:**
@@ -499,7 +494,7 @@ leann remove my-docs
 <details>
 <summary><strong>📋 Click to expand: Complete CLI Reference</strong></summary>
 
-You can use `leann --help`, or `leann build --help`, `leann search --help`, `leann ask --help`, `leann list --help`, `leann remove --help` to get the complete CLI reference.
+You can use `leann --help`, or `leann build --help`, `leann search --help`, `leann ask --help` to get the complete CLI reference.
 
 **Build Command:**
 ```bash
@@ -537,28 +532,6 @@ Options:
   --top-k N                  Retrieval count (default: 20)
 ```
 
-**List Command:**
-```bash
-leann list
-
-# Lists all indexes across all projects with status indicators:
-# ✓ - Index is complete and ready to use
-# ✗ - Index is incomplete or corrupted
-```
-
-**Remove Command:**
-```bash
-leann remove INDEX_NAME [OPTIONS]
-
-Options:
-  --force, -f    Force removal without confirmation
-
-# Smart removal: automatically finds and safely removes indexes
-# - Shows all matching indexes across projects
-# - Requires confirmation for cross-project removal
-# - Interactive selection when multiple matches found
-```
-
 </details>
 
 ## 🏗️ Architecture & How It Works

packages/leann-backend-diskann/pyproject.toml

@@ -4,8 +4,8 @@ build-backend = "scikit_build_core.build"
 
 [project]
 name = "leann-backend-diskann"
-version = "0.3.0"
+version = "0.2.9"
-dependencies = ["leann-core==0.3.0", "numpy", "protobuf>=3.19.0"]
+dependencies = ["leann-core==0.2.9", "numpy", "protobuf>=3.19.0"]
 
 [tool.scikit-build]
 # Key: simplified CMake path

packages/leann-backend-hnsw/pyproject.toml

@@ -6,10 +6,10 @@ build-backend = "scikit_build_core.build"
 
 [project]
 name = "leann-backend-hnsw"
-version = "0.3.0"
+version = "0.2.9"
 description = "Custom-built HNSW (Faiss) backend for the Leann toolkit."
 dependencies = [
-    "leann-core==0.3.0",
+    "leann-core==0.2.9",
     "numpy",
     "pyzmq>=23.0.0",
     "msgpack>=1.0.0",

packages/leann-core/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "leann-core"
-version = "0.3.0"
+version = "0.2.9"
 description = "Core API and plugin system for LEANN"
 readme = "README.md"
 requires-python = ">=3.9"

packages/leann-core/src/leann/api.py

@@ -46,7 +46,6 @@ def compute_embeddings(
             - "sentence-transformers": Use sentence-transformers library (default)
             - "mlx": Use MLX backend for Apple Silicon
             - "openai": Use OpenAI embedding API
-            - "gemini": Use Google Gemini embedding API
         use_server: Whether to use embedding server (True for search, False for build)
 
     Returns:

packages/leann-core/src/leann/chat.py

@@ -680,52 +680,6 @@ class HFChat(LLMInterface):
         return response.strip()
 
 
-class GeminiChat(LLMInterface):
-    """LLM interface for Google Gemini models."""
-
-    def __init__(self, model: str = "gemini-2.5-flash", api_key: Optional[str] = None):
-        self.model = model
-        self.api_key = api_key or os.getenv("GEMINI_API_KEY")
-
-        if not self.api_key:
-            raise ValueError(
-                "Gemini API key is required. Set GEMINI_API_KEY environment variable or pass api_key parameter."
-            )
-
-        logger.info(f"Initializing Gemini Chat with model='{model}'")
-
-        try:
-            import google.genai as genai
-
-            self.client = genai.Client(api_key=self.api_key)
-        except ImportError:
-            raise ImportError(
-                "The 'google-genai' library is required for Gemini models. Please install it with 'uv pip install google-genai'."
-            )
-
-    def ask(self, prompt: str, **kwargs) -> str:
-        logger.info(f"Sending request to Gemini with model {self.model}")
-
-        try:
-            # Set generation configuration
-            generation_config = {
-                "temperature": kwargs.get("temperature", 0.7),
-                "max_output_tokens": kwargs.get("max_tokens", 1000),
-            }
-
-            # Handle top_p parameter
-            if "top_p" in kwargs:
-                generation_config["top_p"] = kwargs["top_p"]
-
-            response = self.client.models.generate_content(
-                model=self.model, contents=prompt, config=generation_config
-            )
-            return response.text.strip()
-        except Exception as e:
-            logger.error(f"Error communicating with Gemini: {e}")
-            return f"Error: Could not get a response from Gemini. Details: {e}"
-
-
 class OpenAIChat(LLMInterface):
     """LLM interface for OpenAI models."""
 
@@ -839,8 +793,6 @@ def get_llm(llm_config: Optional[dict[str, Any]] = None) -> LLMInterface:
         return HFChat(model_name=model or "deepseek-ai/deepseek-llm-7b-chat")
     elif llm_type == "openai":
         return OpenAIChat(model=model or "gpt-4o", api_key=llm_config.get("api_key"))
-    elif llm_type == "gemini":
-        return GeminiChat(model=model or "gemini-2.5-flash", api_key=llm_config.get("api_key"))
     elif llm_type == "simulated":
         return SimulatedChat()
     else:

packages/leann-core/src/leann/cli.py

@@ -84,7 +84,6 @@ Examples:
   leann search my-docs "query"                                           # Search in my-docs index
   leann ask my-docs "question"                                           # Ask my-docs index
   leann list                                                             # List all stored indexes
-  leann remove my-docs                                                   # Remove an index (local first, then global)
             """,
         )
 
@@ -149,12 +148,6 @@ Examples:
             type=str,
             help="Comma-separated list of file extensions to include (e.g., '.txt,.pdf,.pptx'). If not specified, uses default supported types.",
         )
-        build_parser.add_argument(
-            "--include-hidden",
-            action=argparse.BooleanOptionalAction,
-            default=False,
-            help="Include hidden files and directories (paths starting with '.') during indexing (default: false)",
-        )
         build_parser.add_argument(
             "--doc-chunk-size",
             type=int,
@@ -252,13 +245,6 @@ Examples:
         # List command
         subparsers.add_parser("list", help="List all indexes")
 
-        # Remove command
-        remove_parser = subparsers.add_parser("remove", help="Remove an index")
-        remove_parser.add_argument("index_name", help="Index name to remove")
-        remove_parser.add_argument(
-            "--force", "-f", action="store_true", help="Force removal without confirmation"
-        )
-
         return parser
 
     def register_project_dir(self):
@@ -347,6 +333,8 @@ Examples:
             return False
 
     def list_indexes(self):
+        print("Stored LEANN indexes:")
+
         # Get all project directories with .leann
         global_registry = Path.home() / ".leann" / "projects.json"
         all_projects = []
@@ -372,293 +360,58 @@ Examples:
         if (current_path / ".leann" / "indexes").exists() and current_path not in valid_projects:
             valid_projects.append(current_path)
 
-        # Separate current and other projects
+        if not valid_projects:
-        current_project = None
+            print(
-        other_projects = []
+                "No indexes found. Use 'leann build <name> --docs <dir> [<dir2> ...]' to create one."
-
+            )
-        for project_path in valid_projects:
+            return
-            if project_path == current_path:
-                current_project = project_path
-            else:
-                other_projects.append(project_path)
-
-        print("📚 LEANN Indexes")
-        print("=" * 50)
 
         total_indexes = 0
-        current_indexes_count = 0
+        current_dir = Path.cwd()
 
-        # Show current project first (most important)
+        for project_path in valid_projects:
-        if current_project:
+            indexes_dir = project_path / ".leann" / "indexes"
-            current_indexes_dir = current_project / ".leann" / "indexes"
+            if not indexes_dir.exists():
-            if current_indexes_dir.exists():
-                current_index_dirs = [d for d in current_indexes_dir.iterdir() if d.is_dir()]
-
-                print("\n🏠 Current Project")
-                print(f"   {current_project}")
-                print("   " + "─" * 45)
-
-                if current_index_dirs:
-                    for index_dir in current_index_dirs:
-                        total_indexes += 1
-                        current_indexes_count += 1
-                        index_name = index_dir.name
-                        meta_file = index_dir / "documents.leann.meta.json"
-                        status = "✅" if meta_file.exists() else "❌"
-
-                        print(f"   {current_indexes_count}. {index_name} {status}")
-                        if meta_file.exists():
-                            size_mb = sum(
-                                f.stat().st_size for f in index_dir.iterdir() if f.is_file()
-                            ) / (1024 * 1024)
-                            print(f"      📦 Size: {size_mb:.1f} MB")
-                else:
-                    print("   📭 No indexes in current project")
-        else:
-            print("\n🏠 Current Project")
-            print(f"   {current_path}")
-            print("   " + "─" * 45)
-            print("   📭 No indexes in current project")
-
-        # Show other projects (reference information)
-        if other_projects:
-            print("\n\n🗂️  Other Projects")
-            print("   " + "─" * 45)
-
-            for project_path in other_projects:
-                indexes_dir = project_path / ".leann" / "indexes"
-                if not indexes_dir.exists():
-                    continue
-
-                index_dirs = [d for d in indexes_dir.iterdir() if d.is_dir()]
-                if not index_dirs:
-                    continue
-
-                print(f"\n   📂 {project_path.name}")
-                print(f"      {project_path}")
-
-                for index_dir in index_dirs:
-                    total_indexes += 1
-                    index_name = index_dir.name
-                    meta_file = index_dir / "documents.leann.meta.json"
-                    status = "✅" if meta_file.exists() else "❌"
-
-                    print(f"      • {index_name} {status}")
-                    if meta_file.exists():
-                        size_mb = sum(
-                            f.stat().st_size for f in index_dir.iterdir() if f.is_file()
-                        ) / (1024 * 1024)
-                        print(f"        📦 {size_mb:.1f} MB")
-
-        # Summary and usage info
-        print("\n" + "=" * 50)
-        if total_indexes == 0:
-            print("💡 Get started:")
-            print("   leann build my-docs --docs ./documents")
-        else:
-            projects_count = len(
-                [
-                    p
-                    for p in valid_projects
-                    if (p / ".leann" / "indexes").exists()
-                    and list((p / ".leann" / "indexes").iterdir())
-                ]
-            )
-            print(f"📊 Total: {total_indexes} indexes across {projects_count} projects")
-
-            if current_indexes_count > 0:
-                print("\n💫 Quick start (current project):")
-                # Get first index from current project for example
-                current_indexes_dir = current_path / ".leann" / "indexes"
-                if current_indexes_dir.exists():
-                    current_index_dirs = [d for d in current_indexes_dir.iterdir() if d.is_dir()]
-                    if current_index_dirs:
-                        example_name = current_index_dirs[0].name
-                        print(f'   leann search {example_name} "your query"')
-                        print(f"   leann ask {example_name} --interactive")
-            else:
-                print("\n💡 Create your first index:")
-                print("   leann build my-docs --docs ./documents")
-
-    def remove_index(self, index_name: str, force: bool = False):
-        """Safely remove an index - always show all matches for transparency"""
-
-        # Always do a comprehensive search for safety
-        print(f"🔍 Searching for all indexes named '{index_name}'...")
-        all_matches = self._find_all_matching_indexes(index_name)
-
-        if not all_matches:
-            print(f"❌ Index '{index_name}' not found in any project.")
-            return False
-
-        if len(all_matches) == 1:
-            return self._remove_single_match(all_matches[0], index_name, force)
-        else:
-            return self._remove_from_multiple_matches(all_matches, index_name, force)
-
-    def _find_all_matching_indexes(self, index_name: str):
-        """Find all indexes with the given name across all projects"""
-        matches = []
-
-        # Get all registered projects
-        global_registry = Path.home() / ".leann" / "projects.json"
-        all_projects = []
-
-        if global_registry.exists():
-            try:
-                import json
-
-                with open(global_registry) as f:
-                    all_projects = json.load(f)
-            except Exception:
-                pass
-
-        # Always include current project
-        current_path = Path.cwd()
-        if str(current_path) not in all_projects:
-            all_projects.append(str(current_path))
-
-        # Search across all projects
-        for project_dir in all_projects:
-            project_path = Path(project_dir)
-            if not project_path.exists():
                 continue
 
-            index_dir = project_path / ".leann" / "indexes" / index_name
+            index_dirs = [d for d in indexes_dir.iterdir() if d.is_dir()]
-            if index_dir.exists():
+            if not index_dirs:
-                is_current = project_path == current_path
+                continue
-                matches.append(
-                    {"project_path": project_path, "index_dir": index_dir, "is_current": is_current}
-                )
 
-        # Sort: current project first, then by project name
+            # Show project header
-        matches.sort(key=lambda x: (not x["is_current"], x["project_path"].name))
+            if project_path == current_dir:
-        return matches
+                print(f"\n📁 Current project ({project_path}):")
-
-    def _remove_single_match(self, match, index_name: str, force: bool):
-        """Handle removal when only one match is found"""
-        project_path = match["project_path"]
-        index_dir = match["index_dir"]
-        is_current = match["is_current"]
-
-        if is_current:
-            location_info = "current project"
-            emoji = "🏠"
-        else:
-            location_info = f"other project '{project_path.name}'"
-            emoji = "📂"
-
-        print(f"✅ Found 1 index named '{index_name}':")
-        print(f"   {emoji} Location: {location_info}")
-        print(f"   📍 Path: {project_path}")
-
-        if not force:
-            if not is_current:
-                print("\n⚠️  CROSS-PROJECT REMOVAL!")
-                print("   This will delete the index from another project.")
-
-            response = input(f"   ❓ Confirm removal from {location_info}? (y/N): ").strip().lower()
-            if response not in ["y", "yes"]:
-                print("   ❌ Removal cancelled.")
-                return False
-
-        return self._delete_index_directory(
-            index_dir, index_name, project_path if not is_current else None
-        )
-
-    def _remove_from_multiple_matches(self, matches, index_name: str, force: bool):
-        """Handle removal when multiple matches are found"""
-
-        print(f"⚠️  Found {len(matches)} indexes named '{index_name}':")
-        print("   " + "─" * 50)
-
-        for i, match in enumerate(matches, 1):
-            project_path = match["project_path"]
-            is_current = match["is_current"]
-
-            if is_current:
-                print(f"   {i}. 🏠 Current project")
-                print(f"      📍 {project_path}")
             else:
-                print(f"   {i}. 📂 {project_path.name}")
+                print(f"\n📂 {project_path}:")
-                print(f"      📍 {project_path}")
 
-            # Show size info
+            for index_dir in index_dirs:
-            try:
+                total_indexes += 1
-                size_mb = sum(
+                index_name = index_dir.name
-                    f.stat().st_size for f in match["index_dir"].iterdir() if f.is_file()
+                meta_file = index_dir / "documents.leann.meta.json"
-                ) / (1024 * 1024)
+                status = "✓" if meta_file.exists() else "✗"
-                print(f"      📦 Size: {size_mb:.1f} MB")
-            except (OSError, PermissionError):
-                pass
 
-        print("   " + "─" * 50)
+                print(f"  {total_indexes}. {index_name} [{status}]")
+                if status == "✓":
+                    size_mb = sum(f.stat().st_size for f in index_dir.iterdir() if f.is_file()) / (
+                        1024 * 1024
+                    )
+                    print(f"     Size: {size_mb:.1f} MB")
 
-        if force:
+        if total_indexes > 0:
-            print("   ❌ Multiple matches found, but --force specified.")
+            print(f"\nTotal: {total_indexes} indexes across {len(valid_projects)} projects")
-            print("   Please run without --force to choose which one to remove.")
+            print("\nUsage (current project only):")
-            return False
 
-        try:
+            # Show example from current project
-            choice = input(
+            current_indexes_dir = current_dir / ".leann" / "indexes"
-                f"   ❓ Which one to remove? (1-{len(matches)}, or 'c' to cancel): "
+            if current_indexes_dir.exists():
-            ).strip()
+                current_index_dirs = [d for d in current_indexes_dir.iterdir() if d.is_dir()]
-            if choice.lower() == "c":
+                if current_index_dirs:
-                print("   ❌ Removal cancelled.")
+                    example_name = current_index_dirs[0].name
-                return False
+                    print(f'  leann search {example_name} "your query"')
-
+                    print(f"  leann ask {example_name} --interactive")
-            choice_idx = int(choice) - 1
-            if 0 <= choice_idx < len(matches):
-                selected_match = matches[choice_idx]
-                project_path = selected_match["project_path"]
-                index_dir = selected_match["index_dir"]
-                is_current = selected_match["is_current"]
-
-                location = "current project" if is_current else f"'{project_path.name}' project"
-                print(f"   🎯 Selected: Remove from {location}")
-
-                # Final confirmation for safety
-                confirm = input(
-                    f"   ❓ FINAL CONFIRMATION - Type '{index_name}' to proceed: "
-                ).strip()
-                if confirm != index_name:
-                    print("   ❌ Confirmation failed. Removal cancelled.")
-                    return False
-
-                return self._delete_index_directory(
-                    index_dir, index_name, project_path if not is_current else None
-                )
-            else:
-                print("   ❌ Invalid choice. Removal cancelled.")
-                return False
-
-        except (ValueError, KeyboardInterrupt):
-            print("\n   ❌ Invalid input. Removal cancelled.")
-            return False
-
-    def _delete_index_directory(
-        self, index_dir: Path, index_name: str, project_path: Path | None = None
-    ):
-        """Actually delete the index directory"""
-        try:
-            import shutil
-
-            shutil.rmtree(index_dir)
-
-            if project_path:
-                print(f"✅ Index '{index_name}' removed from {project_path.name}")
-            else:
-                print(f"✅ Index '{index_name}' removed successfully")
-            return True
-        except Exception as e:
-            print(f"❌ Error removing index '{index_name}': {e}")
-            return False
 
     def load_documents(
-        self,
+        self, docs_paths: Union[str, list], custom_file_types: Union[str, None] = None
-        docs_paths: Union[str, list],
-        custom_file_types: Union[str, None] = None,
-        include_hidden: bool = False,
     ):
         # Handle both single path (string) and multiple paths (list) for backward compatibility
         if isinstance(docs_paths, str):
@@ -702,10 +455,6 @@ Examples:
 
         all_documents = []
 
-        # Helper to detect hidden path components
-        def _path_has_hidden_segment(p: Path) -> bool:
-            return any(part.startswith(".") and part not in [".", ".."] for part in p.parts)
-
         # First, process individual files if any
         if files:
             print(f"\n🔄 Processing {len(files)} individual file{'s' if len(files) > 1 else ''}...")
@@ -718,12 +467,8 @@ Examples:
 
                 files_by_dir = defaultdict(list)
                 for file_path in files:
-                    file_path_obj = Path(file_path)
+                    parent_dir = str(Path(file_path).parent)
-                    if not include_hidden and _path_has_hidden_segment(file_path_obj):
+                    files_by_dir[parent_dir].append(file_path)
-                        print(f"  ⚠️  Skipping hidden file: {file_path}")
-                        continue
-                    parent_dir = str(file_path_obj.parent)
-                    files_by_dir[parent_dir].append(str(file_path_obj))
 
                 # Load files from each parent directory
                 for parent_dir, file_list in files_by_dir.items():
@@ -734,7 +479,6 @@ Examples:
                         file_docs = SimpleDirectoryReader(
                             parent_dir,
                             input_files=file_list,
-                            # exclude_hidden only affects directory scans; input_files are explicit
                             filename_as_id=True,
                         ).load_data()
                         all_documents.extend(file_docs)
@@ -833,8 +577,6 @@ Examples:
                     # Check if file matches any exclude pattern
                     try:
                         relative_path = file_path.relative_to(docs_path)
-                        if not include_hidden and _path_has_hidden_segment(relative_path):
-                            continue
                         if self._should_exclude_file(relative_path, gitignore_matches):
                             continue
                     except ValueError:
@@ -862,7 +604,6 @@ Examples:
                         try:
                             default_docs = SimpleDirectoryReader(
                                 str(file_path.parent),
-                                exclude_hidden=not include_hidden,
                                 filename_as_id=True,
                                 required_exts=[file_path.suffix],
                             ).load_data()
@@ -891,7 +632,6 @@ Examples:
                     encoding="utf-8",
                     required_exts=code_extensions,
                     file_extractor={},  # Use default extractors
-                    exclude_hidden=not include_hidden,
                     filename_as_id=True,
                 ).load_data(show_progress=True)
 
@@ -1041,9 +781,7 @@ Examples:
             paragraph_separator="\n\n",
         )
 
-        all_texts = self.load_documents(
+        all_texts = self.load_documents(docs_paths, args.file_types)
-            docs_paths, args.file_types, include_hidden=args.include_hidden
-        )
         if not all_texts:
             print("No documents found")
             return
@@ -1180,8 +918,6 @@ Examples:
 
         if args.command == "list":
             self.list_indexes()
-        elif args.command == "remove":
-            self.remove_index(args.index_name, args.force)
         elif args.command == "build":
             await self.build_index(args)
         elif args.command == "search":
@@ -1193,15 +929,10 @@ Examples:
 
 
 def main():
-    import logging
-
     import dotenv
 
     dotenv.load_dotenv()
 
-    # Set clean logging for CLI usage
-    logging.getLogger().setLevel(logging.WARNING)  # Only show warnings and errors
-
     cli = LeannCLI()
     asyncio.run(cli.run())
 

packages/leann-core/src/leann/embedding_compute.py

@@ -57,8 +57,6 @@ def compute_embeddings(
         return compute_embeddings_mlx(texts, model_name)
     elif mode == "ollama":
         return compute_embeddings_ollama(texts, model_name, is_build=is_build)
-    elif mode == "gemini":
-        return compute_embeddings_gemini(texts, model_name, is_build=is_build)
     else:
         raise ValueError(f"Unsupported embedding mode: {mode}")
 
@@ -670,83 +668,3 @@ def compute_embeddings_ollama(
     logger.info(f"Generated {len(embeddings)} embeddings, dimension: {embeddings.shape[1]}")
 
     return embeddings
-
-
-def compute_embeddings_gemini(
-    texts: list[str], model_name: str = "text-embedding-004", is_build: bool = False
-) -> np.ndarray:
-    """
-    Compute embeddings using Google Gemini API.
-
-    Args:
-        texts: List of texts to compute embeddings for
-        model_name: Gemini model name (default: "text-embedding-004")
-        is_build: Whether this is a build operation (shows progress bar)
-
-    Returns:
-        Embeddings array, shape: (len(texts), embedding_dim)
-    """
-    try:
-        import os
-
-        import google.genai as genai
-    except ImportError as e:
-        raise ImportError(f"Google GenAI package not installed: {e}")
-
-    api_key = os.getenv("GEMINI_API_KEY")
-    if not api_key:
-        raise RuntimeError("GEMINI_API_KEY environment variable not set")
-
-    # Cache Gemini client
-    cache_key = "gemini_client"
-    if cache_key in _model_cache:
-        client = _model_cache[cache_key]
-    else:
-        client = genai.Client(api_key=api_key)
-        _model_cache[cache_key] = client
-        logger.info("Gemini client cached")
-
-    logger.info(
-        f"Computing embeddings for {len(texts)} texts using Gemini API, model: '{model_name}'"
-    )
-
-    # Gemini supports batch embedding
-    max_batch_size = 100  # Conservative batch size for Gemini
-    all_embeddings = []
-
-    try:
-        from tqdm import tqdm
-
-        total_batches = (len(texts) + max_batch_size - 1) // max_batch_size
-        batch_range = range(0, len(texts), max_batch_size)
-        batch_iterator = tqdm(
-            batch_range, desc="Computing embeddings", unit="batch", total=total_batches
-        )
-    except ImportError:
-        # Fallback when tqdm is not available
-        batch_iterator = range(0, len(texts), max_batch_size)
-
-    for i in batch_iterator:
-        batch_texts = texts[i : i + max_batch_size]
-
-        try:
-            # Use the embed_content method from the new Google GenAI SDK
-            response = client.models.embed_content(
-                model=model_name,
-                contents=batch_texts,
-                config=genai.types.EmbedContentConfig(
-                    task_type="RETRIEVAL_DOCUMENT"  # For document embedding
-                ),
-            )
-
-            # Extract embeddings from response
-            for embedding_data in response.embeddings:
-                all_embeddings.append(embedding_data.values)
-        except Exception as e:
-            logger.error(f"Batch {i} failed: {e}")
-            raise
-
-    embeddings = np.array(all_embeddings, dtype=np.float32)
-    logger.info(f"Generated {len(embeddings)} embeddings, dimension: {embeddings.shape[1]}")
-
-    return embeddings

packages/leann-core/src/leann/registry.py

@@ -2,15 +2,11 @@
 
 import importlib
 import importlib.metadata
-import logging
 from typing import TYPE_CHECKING
 
 if TYPE_CHECKING:
     from leann.interface import LeannBackendFactoryInterface
 
-# Set up logger for this module
-logger = logging.getLogger(__name__)
-
 BACKEND_REGISTRY: dict[str, "LeannBackendFactoryInterface"] = {}
 
 
@@ -18,7 +14,7 @@ def register_backend(name: str):
     """A decorator to register a new backend class."""
 
     def decorator(cls):
-        logger.debug(f"Registering backend '{name}'")
+        print(f"INFO: Registering backend '{name}'")
         BACKEND_REGISTRY[name] = cls
         return cls
 

packages/leann/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "leann"
-version = "0.3.0"
+version = "0.2.9"
 description = "LEANN - The smallest vector index in the world. RAG Everything with LEANN!"
 readme = "README.md"
 requires-python = ">=3.9"